Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/thepizzapie/buildersgate/claude-mdgit clone --depth 1 https://github.com/Thepizzapie/BuildersGateWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/thepizzapie/buildersgate/claude-md)<a href="https://agentmods.dev/instructions/thepizzapie/buildersgate/claude-md"><img src="https://agentmods.dev/badge/instructions/thepizzapie/buildersgate/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01915 | $0.01915 |
| Opus 5 | $0.00958 | $0.00958 |
| Sonnet 5 | $0.00383 | $0.00383 |
| Haiku 4.5 | $0.00192 | $0.00192 |
Grade A, and why
BuildersGate CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setting up Builders Gate for a user
You have probably been asked something like "set this up for me" or "help me get this running". The user may not know what an MCP server is. Do not explain the architecture unless asked. Get them booted, then point them at docs/start-here.md.
Windows is the supported platform. Linux is best-effort, macOS is untested. Say so if they are on macOS rather than letting them find out.
Ask two things first
- Do they already have a Godot game? This decides
adoptvsinitand it is the single most common thing to get wrong. Scaffolding over someone's existing work is the one unrecoverable mistake available here. - Do they have an image API key?
OPENAI_API_KEYorKREA_API_KEY. If not, everything except art generation still works. Do not block on it.
Install
git clone https://github.com/Thepizzapie/BuildersGate
cd BuildersGate
pip install -e .
bgate doctor
bgate doctor exits 1 if anything on its list is missing, including things
nobody needs on day one. Read the rows, not the exit code. Python and Godot
are what the core loop requires. Blender, ffmpeg and whisper are for the 3D,
playtest-capture and voice paths respectively; a red row there is not a blocker
and you should say that instead of trying to fix it.
The art_key row is green when any art provider is USABLE — keyed AND
with its adapter able to run. That is a narrower question than "is the
variable set", deliberately: it read the second one and printed 4 of 4 providers on a machine whose generation gateway had exactly one live
option. It now says N of M providers usable, and names how many are
merely keyed when the two differ. provider_status is the live read — it
adds account balances and says which provider each job would actually
route to.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday Changed · +15 lines · +178 tokens per session 38e968c8b990
- 5d ago First seen · 175 lines · 1,737 tokens per session scan A 9749145db745
BuildersGate CLAUDE.md is an instructions file published in the GitHub repository Thepizzapie/BuildersGate (24 stars, last pushed today), licensed MIT. It adds 1,915 tokens to every session, about $0.0096 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
build_a_product_agent CLAUDE.md
Instructions for ADW-19/build_a_product_agent, covering claude.md, 项目本质（readme 概览之外）, 目录与编号规范, 文章写作规范（新增/修改文章时必须遵循） and 常用操作.
kungfu AGENTS.md
AGENTS.md instructions for kungfu-systems/kungfu, covering agents.md, start from the person's objective, rules that always apply, load bounded context before changing the repository and execute and verify through shifu.
kungfu CLAUDE.md
Claude Code instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before working in this repository. It routes both product use and contribution work to the repository sources of truth, including the requirement that development and build tasks enter through Shifu.
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
growmos AGENTS.md
Instructions for codician-team/growmos: This repository keeps a knowledge graph in .growmos/ (entities, typed relations, provenance, profiles, a journal). It is the shared world model that survives context windows. Treat it as memory you read at the start of work and write to as you develop. Zero-config commands.
awesome-agent-infrastructure CLAUDE.md
Instructions for backblaze-labs/awesome-agent-infrastructure, covering claude.md — awesome-agent-infrastructure, what this list is, scope and files, schema, workflow, rules.